# US 2019/0377609 A1 · Determining an allocation of stage and destage tasks by using a machine learning module

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0377609 A1
- Document ID: US20190377609A1
- Status: Published application
- Kind: A1
- Application number: 16/004,321
- Filed: 2018-06-08
- Published: 2019-12-12
- Earliest claimed: 2018-06-08
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Lokesh M. Gupta; Kyler A. Anderson; Matthew G. Borlick; Kevin J. Ash
- Web page: https://patentgrep.com/patent/US20190377609A1

## CPC

- G06F 9/5038: {considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups)}
- G06F 12/0868: Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
- G06F 3/061: {Improving I/O performance}
- G06F 3/0659: {Command handling arrangements, e.g. command buffers, queues, command scheduling}
- G06F 3/0689: {Disk arrays, e.g. RAID, JBOD}
- G06F 9/4806: {Task transfer initiation or dispatching}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 20/00: Machine learning
- G06F 2212/1024: Latency reduction
- G06F 2212/1041: Resource optimization
- G06F 2212/262: configured as RAID
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/025: Extracting rules from data
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Provided are a computer program product, system, and method for using a machine learning module to determine an allocation of stage and destage tasks. Storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit is provided to a machine learning module. The machine learning module receives a computed number of stage tasks and a computed number of destage tasks. A current number of stage tasks allocated to stage tracks from the storage unit to the cache is adjusted based on the computed number of stage tasks. A current number of destage tasks allocated to destage tracks from the cache to the storage unit is adjusted based on the computed number of destage tasks.

## Claims

### Claim 1

A computer program product for allocating tasks to stage tracks from a storage unit to a cache and destage tracks from the cache to the storage unit, comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations, the operations comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to a machine learning module;
receiving, from the machine learning module, a computed number of stage tasks and a computed number of destage tasks;
adjusting a current number of stage tasks allocated to stage tracks from the storage unit to the cache based on the computed number of stage tasks; and
adjusting a current number of destage tasks allocated to destage tracks from the cache to the storage unit based on the computed number of destage tasks.

### Claim 2 (depends on 1)

The computer program product of claim 1, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information comprises at least one of:
number of tasks queued for staging operations;
NVS usage;
maximum NVS usage allowed;
response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim 3 (depends on 1)

The computer program product of claim 1, wherein the storage performance information is provided to the machine learning module at a predetermined interval.

### Claim 4 (depends on 1)

The computer program product of claim 1, wherein the operations further comprise:
saving the computed number of stage tasks and the computed number of destage tasks;
wherein the adjusting the current number of stage tasks comprises:
determining whether the current number of stage tasks is less than the computed number of stage tasks;
allocating additional stage tasks up to the computed number of stage tasks in response to the current number of stage tasks being less than the computed number of stage tasks;
wherein the adjusting the current number of destage tasks comprises:
determining whether the current number of destage tasks is less than the computed number of destage tasks; and
allocating additional destage tasks up to the computed number of destage tasks in response to the current number of destage tasks being less than the computed number of destage tasks.

### Claim 5 (depends on 1)

The computer program product of claim 1, wherein the operations further comprise:
in response to a destage task completing a destaging operation, determining whether the current number of destage tasks is less than the computed number of destage tasks;
reusing the destage task that completed the destaging operation to destage tracks from the cache to the storage unit in response to the determining that the current number of destage tasks is less than the computed number of destage tasks; and
freeing the destage task that completed the destaging operation in response to the determining that the current number of destage tasks is greater than the computed number of destage tasks.

### Claim 6 (depends on 1)

The computer program product of claim 1, wherein the operations further comprise:
in response to a stage task completing a staging operation, determining whether the current number of stage tasks is less than the computed number of stage tasks;
reusing the stage task that completed a staging operation to stage tracks from the storage unit to the cache in response to the determining that the current number of stage tasks is less than the computed number of stage tasks; and
freeing the stage task that completed the staging operation in response to the determining that the current number of stage tasks is greater than the computed number of stage tasks.

### Claim 7 (depends on 1)

The computer program product of claim 1, wherein the storage unit comprises a Redundant Array of Independent Disk (RAID) rank of a plurality of RAID ranks, wherein each of the RAID ranks is comprised of storage devices, and wherein there is storage performance information for each of the RAID ranks, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information for each RAID rank of the RAID ranks comprises at least one of:
number of tasks queued for staging operations;
speed of at least one storage device in which the RAID rank is stored;
overall NVS usage of tracks from all the RAID ranks;
NVS usage by the RAID rank;
maximum NVS usage allowed for the RAID rank;
RAID rank response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim at position 8

8-15. (canceled)

### Claim 16

A system for allocating tasks to destaging and staging operations with respect to a storage unit, comprising:
a processor;
a cache implemented in at least one memory device;
a machine learning module; and
a computer readable storage medium having computer readable program code embodied therein that when executed by the processor performs operations, the operations comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to the machine learning module;
receiving, from the machine learning module, a computed number of stage tasks and a computed number of destage tasks;
adjusting a current number of stage tasks allocated to stage tracks from the storage unit to the cache based on the computed number of stage tasks; and
adjusting a current number of destage tasks allocated to destage tracks from the cache to the storage unit based on the computed number of destage tasks.

### Claim 17 (depends on 16)

The system of claim 16, wherein the operations further comprise:
saving the computed number of stage tasks and the computed number of destage tasks;
wherein the adjusting the current number of stage tasks comprises:
determining whether the current number of stage tasks is less than the computed number of stage tasks;
allocating additional stage tasks up to the computed number of stage tasks in response to the current number of stage tasks being less than the computed number of stage tasks;
wherein the adjusting the current number of destage tasks comprises:
determining whether the current number of destage tasks is less than the computed number of destage tasks; and
allocating additional destage tasks up to the computed number of destage tasks in response to the current number of destage tasks being less than the computed number of destage tasks.

### Claim at position 11

18-20. (canceled)

### Claim 21

A method for allocating tasks to stage tracks from a storage unit to a cache and destage tracks from the cache to the storage unit, comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to a machine learning module;
receiving, from the machine learning module, a computed number of stage tasks and a computed number of destage tasks;
adjusting a current number of stage tasks allocated to stage tracks from the storage unit to the cache based on the computed number of stage tasks; and
adjusting a current number of destage tasks allocated to destage tracks from the cache to the storage unit based on the computed number of destage tasks.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
saving the computed number of stage tasks and the computed number of destage tasks;
wherein the adjusting the current number of stage tasks comprises:
determining whether the current number of stage tasks is less than the computed number of stage tasks;
allocating additional stage tasks up to the computed number of stage tasks in response to the current number of stage tasks being less than the computed number of stage tasks;
wherein the adjusting the current number of destage tasks comprises:
determining whether the current number of destage tasks is less than the computed number of destage tasks; and
allocating additional destage tasks up to the computed number of destage tasks in response to the current number of destage tasks being less than the computed number of destage tasks.

### Claim at position 14

23-25. (canceled)

### Claim 26

A computer program product for allocating tasks for a cache operation for a cache storing tracks from a storage unit, comprising a computer readable storage medium having computer readable program code embodied therein that when executed performs operations, the operations comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to a machine learning module;
receiving, from the machine learning module, a computed number of tasks used for the cache operation;
in response to a task completing the cache operation, determining whether a current number of tasks for the cache operation exceed or is less than the computed number of tasks;
reusing the task completing the cache operation for a subsequent instance of the cache operation in response to determining that the current number of tasks is less than the computed number of tasks; and
freeing the task completing the cache operation to be available for a first operation type different from a second operation type of the cache operation in response to determining that the current number of tasks exceeds the computed number of tasks.

### Claim 27 (depends on 26)

The computer program product of claim 26,
wherein in a first instance the first operation type comprises a destaging operation to destage tracks from the cache to the storage unit and the second operation type comprises a staging operation to stage tracks from the storage unit to the cache, and
wherein in a second instance wherein the first operation type comprises the staging operation and the second operation type comprises the destaging operation.

### Claim 28 (depends on 16)

The system of claim 16, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information comprises at least one of:
number of tasks queued for staging operations;
NVS usage;
maximum NVS usage allowed;
response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim 29 (depends on 16)

The system of claim 16, wherein the operations further comprise:
in response to a destage task completing a destaging operation, determining whether the current number of destage tasks is less than the computed number of destage tasks;
reusing the destage task that completed the destaging operation to destage tracks from the cache to the storage unit in response to the determining that the current number of destage tasks is less than the computed number of destage tasks; and
freeing the destage task that completed the destaging operation in response to the determining that the current number of destage tasks is greater than the computed number of destage tasks.

### Claim 30 (depends on 16)

The system of claim 16, wherein the operations further comprise:
in response to a stage task completing a staging operation, determining whether the current number of stage tasks is less than the computed number of stage tasks;
reusing the stage task that completed a staging operation to stage tracks from the storage unit to the cache in response to the determining that the current number of stage tasks is less than the computed number of stage tasks; and
freeing the stage task that completed the staging operation in response to the determining that the current number of stage tasks is greater than the computed number of stage tasks.

### Claim 31 (depends on 16)

The system of claim 16, wherein the storage unit comprises a Redundant Array of Independent Disk (RAID) rank of a plurality of RAID ranks, wherein each of the RAID ranks is comprised of storage devices, and wherein there is storage performance information for each of the RAID ranks, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information for each RAID rank of the RAID ranks comprises at least one of:
number of tasks queued for staging operations;
speed of at least one storage device in which the RAID rank is stored;
overall NVS usage of tracks from all the RAID ranks;
NVS usage by the RAID rank;
maximum NVS usage allowed for the RAID rank;
RAID rank response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim 32

A system for allocating tasks to destaging and staging operations with respect to a storage unit, comprising:
a processor;
a cache implemented in at least one memory device;
a machine learning module; and
a computer readable storage medium having computer readable program code embodied therein that when executed by the processor performs operations, the operations comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to a machine learning module;
receiving, from the machine learning module, a computed number of tasks used for a cache operation;
in response to a task completing the cache operation, determining whether a current number of tasks for the cache operation exceed or is less than the computed number of tasks;
reusing the task completing the cache operation for a subsequent instance of the cache operation in response to determining that the current number of tasks is less than the computed number of tasks; and
freeing the task completing the cache operation to be available for a first operation type different from a second operation type of the cache operation in response to determining that the current number of tasks exceeds the computed number of tasks.

### Claim 33 (depends on 32)

The system of claim 32,
wherein in a first instance the first operation type comprises a destaging operation type to destage tracks from the cache to the storage unit and the second operation type comprises a staging operation to stage tracks from the storage unit to the cache, and
wherein in a second instance wherein the first operation type comprises the staging operation type and the second operation type comprises the destaging operation.

### Claim 34 (depends on 21)

The method of claim 21, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information comprises at least one of:
number of tasks queued for staging operations;
NVS usage;
maximum NVS usage allowed;
response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim 35 (depends on 21)

The method of claim 21, further comprising:
in response to a destage task completing a destaging operation, determining whether the current number of destage tasks is less than the computed number of destage tasks;
reusing the destage task that completed the destaging operation to destage tracks from the cache to the storage unit in response to the determining that the current number of destage tasks is less than the computed number of destage tasks; and
freeing the destage task that completed the destaging operation in response to the determining that the current number of destage tasks is greater than the computed number of destage tasks.

### Claim 36 (depends on 21)

The method of claim 21, further comprising:
in response to a stage task completing a staging operation, determining whether the current number of stage tasks is less than the computed number of stage tasks;
reusing the stage task that completed a staging operation to stage tracks from the storage unit to the cache in response to the determining that the current number of stage tasks is less than the computed number of stage tasks; and
freeing the stage task that completed the staging operation in response to the determining that the current number of stage tasks is greater than the computed number of stage tasks.

### Claim 37 (depends on 21)

The method of claim 21, wherein the storage unit comprises a Redundant Array of Independent Disk (RAID) rank of a plurality of RAID ranks, wherein each of the RAID ranks is comprised of storage devices, and wherein there is storage performance information for each of the RAID ranks, wherein a non-volatile storage (NVS) unit stores modified data in the cache, wherein the storage performance information for each RAID rank of the RAID ranks comprises at least one of:
number of tasks queued for staging operations;
speed of at least one storage device in which the RAID rank is stored;
overall NVS usage of tracks from all the RAID ranks;
NVS usage by the RAID rank;
maximum NVS usage allowed for the RAID rank;
RAID rank response time for processing I/O requests with respect to the storage unit;
device adaptor bandwidth utilized in a device adaptor that transfers data between the cache and the storage unit;
maximum device adaptor bandwidth that is available for transfer of data; and
optimum device adaptor bandwidth.

### Claim 38

A method for allocating tasks to stage tracks from a storage unit to a cache and destage tracks from the cache to the storage unit, comprising:
providing storage performance information related to processing of Input/Output (I/O) requests with respect to the storage unit to a machine learning module;
receiving, from the machine learning module, a computed number of tasks used for the cache operation;
in response to a task completing the cache operation, determining whether a current number of tasks for the cache operation exceed or is less than the computed number of tasks;
reusing the task completing the cache operation for a subsequent instance of the cache operation in response to determining that the current number of tasks is less than the computed number of tasks; and
freeing the task completing the cache operation to be available for a first operation type different from a second operation type of the cache operation in response to determining that the current number of tasks exceeds the computed number of tasks.

### Claim 39 (depends on 38)

The method of claim 38,
wherein in a first instance the first operation type comprises a destaging operation type to destage tracks from the cache to the storage unit and the second operation type comprises a staging operation to stage tracks from the storage unit to the cache, and
wherein in a second instance wherein the first operation type comprises the staging operation type and the second operation type comprises the destaging operation.
